Skip to content

Fix default_sampling_params and simple_workflow #373

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pan-x-c merged 7 commits into from
Nov 12, 2025
Merged

Fix default_sampling_params and simple_workflow #373

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
c929ec8
fix `default_sampling_params` and `simple_workflow`
chenyushuo Nov 10, 2025
c36a09b
fix metric calcuation to aggregate by task_id
chenyushuo Nov 10, 2025
79665e0
apply suggestions
chenyushuo Nov 10, 2025
1e49cfb
add unittest for task aggregated metric calcuation
chenyushuo Nov 11, 2025
3d3a728
Merge branch 'main' of github.com:modelscope/Trinity-RFT into fix/vll…
chenyushuo Nov 11, 2025
47422fe
bug fix for unittest
chenyushuo Nov 11, 2025
f6554fe
revert metric modification
chenyushuo Nov 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions trinity/common/models/vllm_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,6 @@ def __init__(
)
self.default_sampling_params = vllm.SamplingParams(
n=1,
temperature=0.0,
max_tokens=config.max_response_tokens,
min_tokens=config.min_response_tokens,
truncate_prompt_tokens=config.max_prompt_tokens,
skip_special_tokens=True,
Expand Down
18 changes: 10 additions & 8 deletions trinity/common/workflows/workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,13 +190,7 @@ def process_messages_to_experience(self, messages, reward, info={}) -> Experienc
return experience


@WORKFLOWS.register_module("simple_workflow")
class SimpleWorkflow(Workflow):
"""A workflow for simple single-round task."""

can_reset: bool = True
can_repeat: bool = True

class BaseSimpleWorkflow(Workflow):
def __init__(
self,
*,
Expand Down Expand Up @@ -246,6 +240,14 @@ def format_messages(self):
messages.append({"role": "assistant", "content": self.reply_prefix})
return messages


@WORKFLOWS.register_module("simple_workflow")
class SimpleWorkflow(BaseSimpleWorkflow):
"""A workflow for simple single-round task."""

can_reset: bool = True
can_repeat: bool = True

def run(self) -> List[Experience]:
# TODO: Optimize the generate function
messages = self.format_messages()
Expand All @@ -272,7 +274,7 @@ def run(self) -> List[Experience]:


@WORKFLOWS.register_module("async_simple_workflow")
class AsyncSimpleWorkflow(Workflow):
class AsyncSimpleWorkflow(BaseSimpleWorkflow):
is_async: bool = True

async def run_async(self) -> List[Experience]:
Expand Down